DeepInfra
Serverless inference for open-weight models with published cached-input rates, plus dedicated GPUs billed by the minute.
- LLM APIs
- Not documented
- Not documented
- Not documented
Who it suits.
Running open-weight models at the lowest published per-token rates here — DeepSeek-V4-Flash at $0.06 per million input is a fraction of what the lab itself charges — with dedicated H100s at $2.20 an hour if throughput demands it.
Consider something else if…
Only some models carry per-token pricing; the rest bill for inference execution time, which is a different and harder thing to forecast.
Editorial · Palash Bagchi · approved
What the documentation says.
Each value below links to the page it was read from, with the sentence it came from. Criteria DeepInfra does not publish are not listed.
Pricing
Pricing model
Two products on one bill: per-token serverless inference with a separate cached-input rate for each model, and dedicated GPUs billed per minute and invoiced weekly. Models without per-token pricing are billed for inference execution time instead.
Sources (1) →Sources ↓
- Pricing — DeepInfra ↗
“Some of our langauge models offer per token pricing. Most other models are billed for inference execution time. [...] Billed in minute granularity Invoiced weekly”
Read 2026-09-06 · official pricing
Inference
Input price, top model
$1.30 per million input tokens for DeepSeek-V4-Pro, the most expensive model in its catalogue. Cached input is $0.10.
Sources (1) →Sources ↓
- Pricing — DeepInfra ↗
“DeepSeek-V4-Pro 1024k $1.30 / $0.10 cached $2.60”
Read 2026-09-06 · official pricing
Output price, top model
$2.60 per million output tokens for DeepSeek-V4-Pro.
Sources (1) →Sources ↓
- Pricing — DeepInfra ↗
“DeepSeek-V4-Pro 1024k $1.30 / $0.10 cached $2.60”
Read 2026-09-06 · official pricing
Input price, cheapest model
$0.06 per million input tokens for DeepSeek-V4-Flash-0731, with cached input at $0.015 and output at $0.18. DeepSeek itself charges $0.44 at peak for the same checkpoint and Fireworks $0.22.
Sources (1) →Sources ↓
- Pricing — DeepInfra ↗
“DeepSeek-V4-Flash-0731 1024k $0.06 / $0.015 cached $0.18”
Read 2026-09-06 · official pricing
Context window
1024k tokens on the DeepSeek V4 models it serves; 160k on the V3 generation. The window is the model's rather than a platform limit.
Sources (1) →Sources ↓
- Pricing — DeepInfra ↗
“DeepSeek-V4-Pro 1024k [...] DeepSeek-V3.2 160k $0.26 / $0.13 cached $0.38”
Read 2026-09-06 · official pricing
Prompt caching
Supported
Sources (1) →Sources ↓
- Pricing — DeepInfra ↗
“DeepSeek-V4-Pro 1024k $1.30 / $0.10 cached $2.60 [...] DeepSeek-V4-Flash-0731 1024k $0.06 / $0.015 cached $0.18”
Read 2026-09-06 · official pricing
GPU
H100 SXM, per GPU-hour
$2.20 per GPU-hour for a dedicated H100 80GB — below every dedicated cloud in this dataset. A100 80GB is $0.89, H200 $2.69, B200 $3.69. Billed in minute granularity, invoiced weekly.
Sources (1) →Sources ↓
- Pricing — DeepInfra ↗
“A100 80GB $0.89 / GPU-hour H100 80GB $2.20 / GPU-hour H200 141GB $2.69 / GPU-hour B200 180GB $3.69 / GPU-hour B300 270GB $4.89 / GPU-hour [...] Billed in minute granularity Invoiced weekly”
Read 2026-09-06 · official pricing
Largest GPU offered
270GB per GPU on a B300, at $4.89 per GPU-hour.
Sources (1) →Sources ↓
- Pricing — DeepInfra ↗
“B300 270GB $4.89 / GPU-hour”
Read 2026-09-06 · official pricing
When these numbers change, hear about it. Sources are re-checked monthly; a repricing goes out as a short note.
DeepInfra in the news
- DeepInfra and humans& Deploy 1,000-Plus NVIDIA B300 GPUs for AI - konsulteer.com
- DeepInfra and humans& Partner on 1,000-GPU NVIDIA B300 Cluster - HPCwire
- DeepInfra Opens 1.7MW Toronto Data Center With 1,000+ NVIDIA B300 GPUs - StorageReview.com
- DeepInfra Brings Blackwell Inference to Canada: Data Residency Gain, Sovereignty Gap - Tech Times